Instructions to use v000000/MN-12B-Estrella-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use v000000/MN-12B-Estrella-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="v000000/MN-12B-Estrella-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("v000000/MN-12B-Estrella-v1")
model = AutoModelForCausalLM.from_pretrained("v000000/MN-12B-Estrella-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use v000000/MN-12B-Estrella-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "v000000/MN-12B-Estrella-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "v000000/MN-12B-Estrella-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/v000000/MN-12B-Estrella-v1

SGLang

How to use v000000/MN-12B-Estrella-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "v000000/MN-12B-Estrella-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "v000000/MN-12B-Estrella-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "v000000/MN-12B-Estrella-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "v000000/MN-12B-Estrella-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use v000000/MN-12B-Estrella-v1 with Docker Model Runner:
```
docker model run hf.co/v000000/MN-12B-Estrella-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Temperature:
Mistral Nemo likes low temperature between 0.3-0.5

Mistral-Nemo-2407-12B-Estrella-v1

RP Model. Seems coherent and concise but also creative. Big merge using new DELLA technique.

Prompt Format: Seems best with "Mistral Instruct" but ChatML might also work.

[INST] System Message [/INST]

[INST] Name: Let's get started. Please respond based on the information and instructions provided above. [/INST]

<s>[INST] Name: What is your favourite condiment? [/INST]
AssistantName: Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> 
[INST] Name: Do you have mayonnaise recipes? [/INST]

Thanks mradermacher for the quants

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged with a multi-step method using the DELLA, DELLA_LINEAR and SLERP merge algorithms.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

#Step 1 (Part1)
models:
  - model: Sao10K/MN-12B-Lyra-v1
    parameters:
      weight: 0.15
      density: 0.77
  - model: shuttleai/shuttle-2.5-mini
    parameters:
      weight: 0.20
      density: 0.78
  - model: anthracite-org/magnum-12b-v2
    parameters:
      weight: 0.35
      density: 0.85
  - model: nothingiisreal/MN-12B-Celeste-V1.9
    parameters:
      weight: 0.55
      density: 0.90
merge_method: della
base_model: Sao10K/MN-12B-Lyra-v1
parameters:
  int8_mask: true
  epsilon: 0.05
  lambda: 1
dtype: bfloat16
#Step 2 (Part2)
models:
  - model: BeaverAI/mistral-doryV2-12b
    parameters:
      weight: 0.10
      density: 0.4
  - model: unsloth/Mistral-Nemo-Instruct-2407
    parameters:
      weight: 0.20
      density: 0.4
  - model: UsernameJustAnother/Nemo-12B-Marlin-v5
    parameters:
      weight: 0.25
      density: 0.5
  - model: invisietch/Atlantis-v0.1-12B
    parameters:
      weight: 0.3
      density: 0.5
  - model: NeverSleep/Lumimaid-v0.2-12B
    parameters:
      weight: 0.4
      density: 0.8
merge_method: della_linear
base_model: anthracite-org/magnum-12b-v2
parameters:
  int8_mask: true
  epsilon: 0.05
  lambda: 1
dtype: bfloat16
#Step 3 (Estrella)
slices:
  - sources:
      - model: v000000/MN-12B-Part2
        layer_range: [0, 40]
      - model: v000000/MN-12B-Part1
        layer_range: [0, 40]
merge_method: slerp
base_model: v000000/MN-12B-Part1
parameters: #smooth gradient prio part1
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 0.6, 0.1, 0.6, 0.3, 0.8, 0.5]
    - filter: mlp
      value: [0, 0.5, 0.4, 0.3, 0, 0.3, 0.4, 0.7, 0.2, 0.5]
    - value: 0.5
dtype: bfloat16